Triple
T11008929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gilda |
E260196
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Joe Sawyer |
E488545
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Joe Sawyer | Statement: [Gilda, starring, Joe Sawyer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Sawyer Context triple: [Gilda, starring, Joe Sawyer]
-
A.
Joe Sawyer
chosen
Joe Sawyer was a Canadian-born character actor known for his tough-guy roles in numerous American films and television shows from the 1930s through the 1960s.
-
B.
Matt Sawyer
Matt Sawyer is a Canadian lacrosse coach best known for leading the Toronto Rock in the National Lacrosse League.
-
C.
Sid Sawyer
Sid Sawyer is Tom Sawyer’s well-behaved but tattling half-brother in Mark Twain’s classic novel "The Adventures of Tom Sawyer."
-
D.
Jack Seddon
Jack Seddon was a screenwriter best known for his work on the epic World War II film "The Longest Day."
-
E.
Cam Fowler
Cam Fowler is an American professional ice hockey defenseman in the NHL, best known for his long tenure with the Anaheim Ducks after starring as a top junior player.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7978810208190b8e2966ae67b6314 |
completed | April 9, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e37498b9fc8190860acede4f49ea4a |
completed | April 18, 2026, 12:10 p.m. |
Created at: April 8, 2026, 9:25 p.m.